Fundamentals of Deep Learning

Index

A

• acceleration, Momentum-Based Optimization
• Actor-Critic methods, Asynchronous Advantage Actor-Critic Agent (A3C)
• AdaDelta, The Philosophy Behind Optimizer Selection
• AdaGrad, AdaGrad—Accumulating Historical Gradients-AdaGrad—Accumulating Historical Gradients
• Adam optimization, Adam—Combining Momentum and RMSProp, The Philosophy Behind Optimizer Selection, Closing the Loop on MNIST with Convolutional Networks, Building a Convolutional Network for CIFAR-10, Implementing a Part-of-Speech Tagger, Building the Model and Optimizer
• add_episode(), Implementing Experience Replay
• advantage function, Asynchronous Advantage Actor-Critic Agent (A3C)
• ae.decoder(), Implementing an Autoencoder in TensorFlow
• ae.encoder(), Implementing an Autoencoder in TensorFlow
• ae.evaluate(), Implementing an Autoencoder in TensorFlow
• ae.loss(), Implementing an Autoencoder in TensorFlow
• AlexNet, The Shortcomings of Feature Selection
• allocation weighting, Interference-Free Writing in DNCs, DNC Memory Reuse, Implementing the DNC in TensorFlow, Implementing the DNC in TensorFlow-Implementing the DNC in TensorFlow
• allow_soft_placement, Managing Models over the CPU and GPU
• alpha, How Pesky Are Spurious Local Minima in Deep Networks?
• annealed e-Greedy policy, Annealed  ϵ -Greedy, PGAgent Performance on Pole-Cart
• approximate per-image whitening, Image Preprocessing Pipelines Enable More Robust Models
• arc-standard system, Dependency Parsing and SyntaxNet
• artificial neural networks (ANNs), Feed-Forward Neural Networks
• Asynchronous Advantage ...